add documentation example for LoRA overlap loading and cleanup unused function (#17464)

2026-01-24 15:33:16 +08:00
parent 3992a023e6
commit a6280b2a23
5 changed files with 140 additions and 16 deletions
@@ -1424,13 +1424,13 @@ class ModelRunner(ModelRunnerKVCacheMixin):
            max_loras_per_batch=self.server_args.max_loras_per_batch,
            load_config=self.load_config,
            dtype=self.dtype,
+            server_args=self.server_args,
            lora_backend=self.server_args.lora_backend,
            tp_size=self.tp_size,
            tp_rank=self.tp_rank,
            max_lora_rank=self.server_args.max_lora_rank,
            target_modules=self.server_args.lora_target_modules,
            lora_paths=self.server_args.lora_paths,
-            server_args=self.server_args,
        )

    def load_lora_adapter(self, lora_ref: LoRARef):